I think what ultimately will matter in this context is that it needs to be consistent for each study. I see the argument with either the resid SD or the raw within group SD, but I would worry about a meta-analyst mixing and matching them in a meta-analysis

Wanna write a meta-analysis error report? matthewbjane.quarto.pub/meta-analysi...

No a meta-meta-analysis-analysis

I think my reaction to the first time I saw it was something along the lines of “wait you can just do that?”

Yeah I might do that. Maybe I’ll make it into a pre-print for now

I’ve been hearing it’s good. No spoilers please, still gotta watch it

Most meta-analyses are bad, some are useful

We tried to. Best we can do for now is submit to meta-psychology and post a pub-peer comment

Nah y’all are right.

What does the pin emoji do?

Don’t do it

livefreeordichotomize.com by @lucystats.bsky.social

matthewbjane.github.io/blog.html by @matthewbjane.bsky.social

www.andrewheiss.com/blog/ by the king @andrew.heiss.phd

ngreifer.github.io/blog/ by yours truly (can't resist a self-promotion 😉)

Stats blogs are the best!